LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
sa

Sarvam 105B

sarvam·sarvam/sarvam-105b·GA·Open weights·sarvam series
Flagship Indian-language reasoning model for enterprise multilingual applications

Specs & pricing

Input / output per 1M tokens
Official price
Price undisclosed
Lowest paid·FastRouterGateway
$0.04 / $0.16
Blended $0.07 · 1.3× spread
Context
131,072
Output limit
131,072
Knowledge cutoff
—
Released / updated
2025-09-01 / 2025-09-01
Capabilities
✓ Reasoning✓ Tool useStructured output✓ TemperatureAttachments
Modalities
Text

Quality & performanceArtificial Analysis · Intelligence Index v4.3 · rep. tier High

Intelligence8.8
Value126
Coding—
Agentic—
Output speed—
TTFT—
Value formulaIQ 8.8 ÷ min blended $0.070 = 126

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 3 providers2 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
FastRouterGateway$0.04$0.16——131,072131,072
NanoGPTGateway$0.054$0.21$0.034—131,0724,096
Sarvam AIOfficialFirst-party————131,072131,072hostTable.undisclosed

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = loweffort = mediumeffort = higheffort = null

Interleaved thinking (reasoning between tool calls) is declared by 1 of 3 providers.

1 / 3 providers expose no reasoning control (reasoning_options: []).

Your usage cost

1FastRouter$16.00
2NanoGPT$18.97
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.07$02026-08-052026-08-132026-08-05 · Min blended $0.072026-08-06 · Min blended $0.072026-08-07 · Min blended $0.072026-08-08 · Min blended $0.072026-08-09 · Min blended $0.072026-08-10 · Min blended $0.072026-08-11 · Min blended $0.072026-08-12 · Min blended $0.072026-08-13 · Min blended $0.07

Artificial Analysis evaluations6 items

GPQA Diamond73.8%
Humanity's Last Exam11.0%
Terminal-Bench Hard1.5%
τ²-Bench Telecom46.8%
AA-LCR0.0%
IFBench34.4%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.

Related models

saSarvam 30Bsame series—
Data partly from models.dev (MIT)